Evidence Explorer

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [On Treatment (Stratification) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
10,688	17,132	13,110	22,949	115	149	8.77	6.49	1.43

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	187	209	312	753	937	2,177
Comparator	2	207	235	344	826	1,030	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Stroke (LEGEND Version) [On Treatment (Stratification) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
10,688	17,132	13,107	22,933	99	184	7.55	8.02	1.41

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	10	188	209	312	752	935	2,177
Comparator	5	207	235	343	824	1,029	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [Intent-to-Treat (Matching) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
7,658	7,658	20,963	20,704	195	175	9.30	8.45	1.34

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	202	474	969	1,731	1,862	2,188
Comparator	11	196	458	936	1,712	1,847	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Stroke (LEGEND Version) [Intent-to-Treat (Matching) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
7,658	7,658	20,992	20,643	176	198	8.38	9.59	1.34

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	10	202	475	972	1,733	1,863	2,188
Comparator	8	194	453	935	1,710	1,840	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Stroke (LEGEND Version) [On Treatment (Matching) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
7,660	7,660	9,627	9,363	64	73	6.65	7.80	1.61

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	14	203	209	315	774	976	2,177
Comparator	8	182	220	322	741	916	2,184

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [On Treatment (Matching) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
7,660	7,660	9,638	9,359	74	73	7.68	7.80	1.59

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	203	209	315	775	976	2,177
Comparator	2	182	221	322	742	914	2,184

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Stroke (LEGEND Version) [Intent-to-Treat (Stratification) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
10,688	17,132	28,205	54,618	265	454	9.40	8.31	1.24

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	10	188	445	907	1,697	1,833	2,189
Comparator	5	265	614	1,221	1,911	2,029	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [Intent-to-Treat (Stratification) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
10,688	17,132	28,176	54,714	277	421	9.83	7.69	1.24

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	188	441	902	1,698	1,833	2,189
Comparator	2	270	620	1,222	1,911	2,029	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [On Treatment (Matching) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
7,665	7,665	9,649	9,282	78	67	8.08	7.22	1.59

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	201	209	315	777	975	2,177
Comparator	9	181	222	320	732	897	2,177

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Stroke (LEGEND Version) [On Treatment (Matching) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
7,665	7,665	9,638	9,275	70	81	7.26	8.73	1.58

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	10	201	209	315	776	972	2,177
Comparator	5	180	220	319	731	898	2,177

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [On Treatment (Stratification) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
10,688	17,132	13,110	22,949	115	149	8.77	6.49	1.43

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	187	209	312	753	937	2,177
Comparator	2	207	235	344	826	1,030	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Stroke (LEGEND Version) [On Treatment (Stratification) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
10,688	17,132	13,107	22,933	99	184	7.55	8.02	1.41

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	10	188	209	312	752	935	2,177
Comparator	5	207	235	343	824	1,029	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [Intent-to-Treat (Matching) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
7,667	7,667	21,155	20,635	193	178	9.12	8.63	1.34

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	209	480	984	1,733	1,862	2,188
Comparator	11	193	452	935	1,707	1,841	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Stroke (LEGEND Version) [Intent-to-Treat (Matching) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
7,667	7,667	21,158	20,602	191	192	9.03	9.32	1.33

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	10	209	481	986	1,733	1,862	2,188
Comparator	5	191	448	934	1,708	1,841	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [Intent-to-Treat (Stratification) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
10,688	17,132	28,176	54,714	277	421	9.83	7.69	1.24

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	188	441	902	1,698	1,833	2,189
Comparator	2	270	620	1,222	1,911	2,029	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Stroke (LEGEND Version) [Intent-to-Treat (Stratification) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
10,688	17,132	28,205	54,618	265	454	9.40	8.31	1.24

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	10	188	445	907	1,697	1,833	2,189
Comparator	5	265	614	1,221	1,911	2,029	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Etanercept (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Adalimumab (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [On Treatment (Stratification) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
10,454	20,386	12,847	25,958	117	183	9.11	7.05	1.41

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	188	209	312	754	943	2,177
Comparator	4	207	232	333	777	970	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Adalimumab (RCT) ~ Stroke (LEGEND Version) [On Treatment (Stratification) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
10,454	20,386	12,850	25,924	97	189	7.55	7.29	1.42

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	10	189	209	312	754	941	2,177
Comparator	2	207	232	332	776	969	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Adalimumab (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [Intent-to-Treat (Matching) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
8,216	8,216	22,084	21,878	213	203	9.64	9.28	1.32

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	196	462	931	1,711	1,848	2,188
Comparator	4	180	441	931	1,693	1,838	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Adalimumab (RCT) ~ Stroke (LEGEND Version) [Intent-to-Treat (Matching) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
8,216	8,216	22,112	21,879	200	193	9.04	8.82	1.33

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	10	199	466	937	1,707	1,846	2,188
Comparator	2	182	441	928	1,695	1,840	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Adalimumab (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [On Treatment (Matching) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
8,210	8,210	10,198	9,704	93	82	9.12	8.45	1.53

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	194	209	315	770	950	2,177
Comparator	4	174	212	312	707	878	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Adalimumab (RCT) ~ Stroke (LEGEND Version) [On Treatment (Matching) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
8,210	8,210	10,203	9,684	75	82	7.35	8.47	1.56

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	10	194	209	314	770	949	2,177
Comparator	2	174	212	312	706	877	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Adalimumab (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [Intent-to-Treat (Stratification) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
10,454	20,386	27,779	60,382	276	455	9.94	7.54	1.24

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	189	447	915	1,705	1,838	2,189
Comparator	4	231	550	1,098	1,797	1,952	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Adalimumab (RCT) ~ Stroke (LEGEND Version) [Intent-to-Treat (Stratification) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
10,454	20,386	27,803	60,337	263	449	9.46	7.44	1.25

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	10	192	451	920	1,704	1,838	2,189
Comparator	2	230	547	1,097	1,798	1,952	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Adalimumab (RCT) ~ Stroke (LEGEND Version) [On Treatment (Matching) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
8,210	8,210	10,153	9,644	78	79	7.68	8.19	1.56

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	10	195	209	313	761	946	2,177
Comparator	15	179	213	313	706	874	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Adalimumab (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [On Treatment (Matching) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
8,210	8,210	10,153	9,649	88	88	8.67	9.12	1.53

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	195	209	313	762	946	2,177
Comparator	4	175	213	313	707	876	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Adalimumab (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [On Treatment (Stratification) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
10,454	20,386	12,847	25,958	117	183	9.11	7.05	1.41

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	188	209	312	754	943	2,177
Comparator	4	207	232	333	777	970	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Adalimumab (RCT) ~ Stroke (LEGEND Version) [On Treatment (Stratification) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
10,454	20,386	12,850	25,924	97	189	7.55	7.29	1.42

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	10	189	209	312	754	941	2,177
Comparator	2	207	232	332	776	969	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Adalimumab (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [Intent-to-Treat (Matching) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
8,211	8,211	22,105	22,110	214	186	9.68	8.41	1.32

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	199	461	938	1,712	1,845	2,188
Comparator	4	180	447	944	1,715	1,858	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Adalimumab (RCT) ~ Stroke (LEGEND Version) [Intent-to-Treat (Matching) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
8,211	8,211	22,134	22,086	203	182	9.17	8.24	1.33

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	10	200	464	942	1,712	1,845	2,188
Comparator	7	179	446	942	1,718	1,861	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Adalimumab (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [Intent-to-Treat (Stratification) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
10,454	20,386	27,779	60,382	276	455	9.94	7.54	1.24

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	189	447	915	1,705	1,838	2,189
Comparator	4	231	550	1,098	1,797	1,952	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RCT) vs. Adalimumab (RCT) ~ Stroke (LEGEND Version) [Intent-to-Treat (Stratification) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
10,454	20,386	27,803	60,337	263	449	9.46	7.44	1.25

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	10	192	451	920	1,704	1,838	2,189
Comparator	2	230	547	1,097	1,798	1,952	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RCT)) and comparator (Adalimumab (RCT)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. [TOFA]_RWD_ETN_0208version ~ Acute Myocardial Infarction (LEGEND Version) [On Treatment (Stratification) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
34,961	71,261	43,059	97,478	286	412	6.64	4.23	1.25

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	186	209	313	753	943	2,189
Comparator	2	207	235	348	848	1,062	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. [TOFA]_RWD_ETN_0208version ~ Stroke (LEGEND Version) [On Treatment (Stratification) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
34,961	71,261	43,042	97,443	265	453	6.16	4.65	1.25

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	186	209	313	753	943	2,189
Comparator	1	207	235	348	849	1,062	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. [TOFA]_RWD_ETN_0208version ~ Acute Myocardial Infarction (LEGEND Version) [Intent-to-Treat (Matching) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
26,474	26,474	74,886	72,547	506	506	6.76	6.97	1.19

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	195	476	1,025	1,791	1,915	2,190
Comparator	2	165	447	963	1,748	1,908	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. [TOFA]_RWD_ETN_0208version ~ Stroke (LEGEND Version) [Intent-to-Treat (Matching) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
26,474	26,474	74,886	72,520	497	483	6.64	6.66	1.20

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	196	476	1,025	1,788	1,914	2,190
Comparator	2	165	446	963	1,748	1,909	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. [TOFA]_RWD_ETN_0208version ~ Acute Myocardial Infarction (LEGEND Version) [On Treatment (Matching) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
26,465	26,465	32,899	32,099	203	180	6.17	5.61	1.33

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	192	209	313	761	959	2,189
Comparator	2	167	209	317	736	912	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. [TOFA]_RWD_ETN_0208version ~ Stroke (LEGEND Version) [On Treatment (Matching) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
26,465	26,465	32,891	32,075	187	197	5.69	6.14	1.33

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	192	209	313	761	961	2,189
Comparator	2	166	209	316	735	914	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. [TOFA]_RWD_ETN_0208version ~ Acute Myocardial Infarction (LEGEND Version) [Intent-to-Treat (Stratification) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
34,961	71,261	96,598	239,487	699	1,196	7.24	4.99	1.15

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	187	459	979	1,767	1,896	2,190
Comparator	2	273	668	1,309	1,994	2,091	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. [TOFA]_RWD_ETN_0208version ~ Stroke (LEGEND Version) [Intent-to-Treat (Stratification) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
34,961	71,261	96,529	239,321	686	1,188	7.11	4.96	1.15

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	187	459	978	1,763	1,895	2,190
Comparator	1	272	665	1,308	1,995	2,091	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. [TOFA]_RWD_ETN_0208version ~ Stroke (LEGEND Version) [On Treatment (Matching) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
26,450	26,450	32,793	31,940	189	202	5.76	6.32	1.33

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	193	209	313	756	953	2,189
Comparator	2	165	209	317	733	906	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. [TOFA]_RWD_ETN_0208version ~ Acute Myocardial Infarction (LEGEND Version) [On Treatment (Matching) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
26,450	26,450	32,799	31,969	202	184	6.16	5.76	1.33

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	193	209	314	756	953	2,189
Comparator	2	166	209	317	733	906	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. [TOFA]_RWD_ETN_0208version ~ Acute Myocardial Infarction (LEGEND Version) [On Treatment (Stratification) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
34,961	71,261	43,059	97,478	286	412	6.64	4.23	1.25

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	186	209	313	753	943	2,189
Comparator	2	207	235	348	848	1,062	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. [TOFA]_RWD_ETN_0208version ~ Stroke (LEGEND Version) [On Treatment (Stratification) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
34,961	71,261	43,042	97,443	265	453	6.16	4.65	1.25

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	186	209	313	753	943	2,189
Comparator	1	207	235	348	849	1,062	2,189

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. [TOFA]_RWD_ETN_0208version ~ Stroke (LEGEND Version) [Intent-to-Treat (Matching) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
26,459	26,459	74,875	72,553	507	491	6.77	6.77	1.19

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	196	479	1,026	1,785	1,911	2,190
Comparator	2	166	441	966	1,743	1,909	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. [TOFA]_RWD_ETN_0208version ~ Acute Myocardial Infarction (LEGEND Version) [Intent-to-Treat (Matching) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
26,459	26,459	74,906	72,644	512	504	6.84	6.94	1.19

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	195	479	1,026	1,789	1,915	2,190
Comparator	2	166	445	968	1,746	1,910	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. [TOFA]_RWD_ETN_0208version ~ Acute Myocardial Infarction (LEGEND Version) [Intent-to-Treat (Stratification) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
34,961	71,261	96,598	239,487	699	1,196	7.24	4.99	1.15

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	187	459	979	1,767	1,896	2,190
Comparator	2	273	668	1,309	1,994	2,091	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. [TOFA]_RWD_ETN_0208version ~ Stroke (LEGEND Version) [Intent-to-Treat (Stratification) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
34,961	71,261	96,529	239,321	686	1,188	7.11	4.96	1.15

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	187	459	978	1,763	1,895	2,190
Comparator	1	272	665	1,308	1,995	2,091	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator ([TOFA]_RWD_ETN_0208version) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. Adalimumab (RWD) ~ Acute Myocardial Infarction (LEGEND Version) [On Treatment (Stratification) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
34,087	84,210	42,037	107,815	279	475	6.64	4.41	1.25

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	189	209	313	753	943	2,189
Comparator	1	207	235	335	771	966	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. Adalimumab (RWD) ~ Stroke (LEGEND Version) [On Treatment (Stratification) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
34,087	84,210	42,027	107,767	254	499	6.04	4.63	1.25

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	2	189	209	313	753	943	2,189
Comparator	2	207	235	335	770	966	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. Adalimumab (RWD) ~ Acute Myocardial Infarction (LEGEND Version) [Intent-to-Treat (Matching) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
27,388	27,388	76,492	75,418	516	541	6.75	7.17	1.19

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	192	466	1,001	1,776	1,904	2,190
Comparator	1	167	444	976	1,761	1,917	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. Adalimumab (RWD) ~ Stroke (LEGEND Version) [Intent-to-Treat (Matching) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
27,388	27,388	76,437	75,430	509	513	6.66	6.80	1.19

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	2	192	466	1,000	1,775	1,903	2,190
Comparator	3	167	444	976	1,760	1,916	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. Adalimumab (RWD) ~ Acute Myocardial Infarction (LEGEND Version) [On Treatment (Matching) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
27,393	27,393	33,761	32,370	215	205	6.37	6.33	1.31

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	189	209	312	753	945	2,189
Comparator	1	173	222	316	702	865	2,188

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. Adalimumab (RWD) ~ Stroke (LEGEND Version) [On Treatment (Matching) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
27,393	27,393	33,764	32,350	186	213	5.51	6.58	1.32

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	2	190	209	312	753	946	2,189
Comparator	2	173	222	315	701	865	2,188

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. Adalimumab (RWD) ~ Acute Myocardial Infarction (LEGEND Version) [Intent-to-Treat (Stratification) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
34,087	84,210	94,965	259,322	690	1,259	7.27	4.85	1.15

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	192	465	991	1,775	1,904	2,190
Comparator	1	240	577	1,169	1,876	2,005	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. Adalimumab (RWD) ~ Stroke (LEGEND Version) [Intent-to-Treat (Stratification) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
34,087	84,210	94,899	259,223	671	1,253	7.07	4.83	1.15

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	2	192	465	991	1,771	1,903	2,190
Comparator	2	238	574	1,169	1,876	2,005	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. Adalimumab (RWD) ~ Stroke (LEGEND Version) [On Treatment (Matching) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
27,372	27,372	33,741	32,278	184	213	5.45	6.60	1.32

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	6	193	209	312	753	945	2,189
Comparator	3	172	221	315	701	871	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. Adalimumab (RWD) ~ Acute Myocardial Infarction (LEGEND Version) [On Treatment (Matching) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
27,372	27,372	33,739	32,306	203	204	6.02	6.31	1.32

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	193	209	312	753	945	2,189
Comparator	1	172	221	315	702	872	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. Adalimumab (RWD) ~ Acute Myocardial Infarction (LEGEND Version) [On Treatment (Stratification) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
34,087	84,210	42,037	107,815	279	475	6.64	4.41	1.25

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	189	209	313	753	943	2,189
Comparator	1	207	235	335	771	966	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. Adalimumab (RWD) ~ Stroke (LEGEND Version) [On Treatment (Stratification) - Original Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
34,087	84,210	42,027	107,767	254	499	6.04	4.63	1.25

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	2	189	209	313	753	943	2,189
Comparator	2	207	235	335	770	966	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. Adalimumab (RWD) ~ Stroke (LEGEND Version) [Intent-to-Treat (Matching) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
27,372	27,372	76,466	75,012	513	515	6.71	6.87	1.19

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	6	194	468	1,001	1,771	1,902	2,190
Comparator	3	173	445	966	1,749	1,904	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. Adalimumab (RWD) ~ Acute Myocardial Infarction (LEGEND Version) [Intent-to-Treat (Matching) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
27,372	27,372	76,508	75,102	511	514	6.68	6.84	1.19

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	194	468	1,004	1,775	1,903	2,190
Comparator	1	173	445	969	1,753	1,907	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. Adalimumab (RWD) ~ Acute Myocardial Infarction (LEGEND Version) [Intent-to-Treat (Stratification) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
34,087	84,210	94,965	259,322	690	1,259	7.27	4.85	1.15

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	1	192	465	991	1,775	1,904	2,190
Comparator	1	240	577	1,169	1,876	2,005	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Kaplan-Meier

Tofacitinib (RWD) vs. Adalimumab (RWD) ~ Stroke (LEGEND Version) [Intent-to-Treat (Stratification) - New Exclusion Covariates, Open Claims]

Power

Target subjects	Comparator subjects	Target years	Comparator years	Target events	Comparator events	Target IR (per 1,000 PY)	Comparator IR (per 1,000 PY)	MDRR
34,087	84,210	94,899	259,223	671	1,253	7.07	4.83	1.15

Table 1a. Number of subjects, follow-up time (in years), number of outcome events, and event incidence rate (IR) per 1,000 patient years (PY) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after propensity score adjustment, as well as the minimum detectable relative risk (MDRR). Note that the IR does not account for any stratification.

Cohort	Min	P10	P25	Median	P75	P90	Max
Target	2	192	465	991	1,771	1,903	2,190
Comparator	2	238	574	1,169	1,876	2,005	2,190

Table 1b. Time (days) at risk distribution expressed as minimum (min), 25th percentile (P25), median, 75th percentile (P75), and maximum (max) in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) cohort after propensity score adjustment.

Attrition

Figure 1. Attrition diagram, showing the Number of subjectsin the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group after various stages in the analysis.

Population Characteristics

Table 2. Select characteristics before and after propensity score adjustment, showing the (weighted) percentage of subjects with the characteristics in the target (Tofacitinib (RWD)) and comparator (Adalimumab (RWD)) group, as well as the standardized difference of the means.

Propensity Scores

Figure 2. Preference score distribution. The preference score is a transformation of the propensity score that adjusts for differences in the sizes of the two treatment groups. A higher overlap indicates subjects in the two groups were more similar in terms of their predicted probability of receiving one treatment over the other.

Covariate Balance

Systematic Error

Figure 4. Systematic error. Effect size estimates for the negative controls (true hazard ratio = 1) and positive controls (true hazard ratio > 1), before and after calibration. Estimates below the diagonal dashed lines are statistically significant (alpha = 0.05) different from the true effect size. A well-calibrated estimator should have the true effect size within the 95 percent confidence interval 95 percent of times.

Evidence Explorer

Results Summary

Target vs. Comparator ~ Outcome [Analysis, DB]:

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [On Treatment (Stratification) - New Exclusion Covariates, Open Claims]

Power

Attrition

Population Characteristics

Propensity Scores

Covariate Balance

Systematic Error

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Stroke (LEGEND Version) [On Treatment (Stratification) - New Exclusion Covariates, Open Claims]

Power

Attrition

Population Characteristics

Propensity Scores

Covariate Balance

Systematic Error

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [Intent-to-Treat (Matching) - Original Covariates, Open Claims]

Power

Attrition

Population Characteristics

Propensity Scores

Covariate Balance

Systematic Error

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Stroke (LEGEND Version) [Intent-to-Treat (Matching) - Original Covariates, Open Claims]

Power

Attrition

Population Characteristics

Propensity Scores

Covariate Balance

Systematic Error

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Stroke (LEGEND Version) [On Treatment (Matching) - Original Covariates, Open Claims]

Power

Attrition

Population Characteristics

Propensity Scores

Covariate Balance

Systematic Error

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [On Treatment (Matching) - Original Covariates, Open Claims]

Power

Attrition

Population Characteristics

Propensity Scores

Covariate Balance

Systematic Error

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Stroke (LEGEND Version) [Intent-to-Treat (Stratification) - Original Covariates, Open Claims]

Power

Attrition

Population Characteristics

Propensity Scores

Covariate Balance

Systematic Error

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [Intent-to-Treat (Stratification) - Original Covariates, Open Claims]

Power

Attrition

Population Characteristics

Propensity Scores

Covariate Balance

Systematic Error

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Acute Myocardial Infarction (LEGEND Version) [On Treatment (Matching) - New Exclusion Covariates, Open Claims]

Power

Attrition

Population Characteristics

Propensity Scores

Covariate Balance

Systematic Error

Kaplan-Meier

Tofacitinib (RCT) vs. Etanercept (RCT) ~ Stroke (LEGEND Version) [On Treatment (Matching) - New Exclusion Covariates, Open Claims]

Power

Attrition

Population Characteristics

Propensity Scores